benchgap
Calibration

Terminal-Bench Science 0.1 → Terminal-Bench 2.1

Terminal-Bench 2.1 is estimated from Terminal-Bench Science 0.1 with a Hill curve fitted on 10 models measured on both: y = 0.5510 + (0.9215 − 0.5510)·x^0.60 / (0.00613^0.60 + x^0.60), R² = 0.89, cross-validated error 7.0 pp. It is used for 2 estimates.

Estimated modelTerminal-Bench Science 0.1Terminal-Bench 2.1Source
Claude Opus 5.5 (medium with fallback)43.3%89.4%estimated ± 7.0 pp, medium confidence
Claude Sonnet 5.5 (high with fallback)34.3%89.1%estimated ± 7.0 pp, medium confidence